Stacked encoder–decoder transformer with boundary smoothing for action segmentation
Abstract In this work, a new stacked encoder–decoder transformer (SEDT) model is proposed for action segmentation. SEDT is composed of a series of encoder–decoder modules, each of which consists of an encoder with self‐attention layers and a decoder with cross‐attention layers. By adding an encoder...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-12-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ell2.12678 |